Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images

This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth the behavior of a state-of-the-art semi-supervised method, FixMatch, which relies on a weakly-augmented version of an image to obtain supervision signal for a more stronglyaugmented version. We show that it frequently fails in barelysupervised scenarios, due to a lack of training signal when no pseudo-label can be predicted with high confidence. We propose a method to leverage self-supervised methods that provides training signal in the absence of confident pseudolabels. We then propose two methods to refine the pseudolabel selection process which lead to further improvements. The first one relies on a per-sample history of the model predictions, akin to a voting scheme. The second iteratively updates class-dependent confidence thresholds to better explore classes that are under-represented in the pseudo-labels. Our experiments show that our approach performs significantly better on STL-10 in the barely-supervised regime, e. g. with 4 or 8 labeled images per class.

Authors

• Thomas Lucas
• Philippe Weinzaepfel
• Gregory Rogez

Keywords

No keywords are indexed for this paper.